def test_hdp_dense_input():
"""Dense and sparse input should be the same"""
X = make_uniform_doc_word_matrix(n_topics=10,
words_per_topic=3,
docs_per_topic=3)
dense_X = X.todense()
array_X = X.toarray()
params = {
'n_topic_truncate': 20,
'n_doc_truncate': 5,
'learning_method': 'batch',
'max_iter': 10,
'random_state': 1,
}
hdp1 = HierarchicalDirichletProcess(**params)
transformed_1 = hdp1.fit_transform(dense_X)
hdp2 = HierarchicalDirichletProcess(**params)
transformed_2 = hdp2.fit_transform(array_X)
hdp3 = HierarchicalDirichletProcess(**params)
transformed_3 = hdp3.fit_transform(X)
assert_almost_equal(transformed_1, transformed_2)
assert_almost_equal(transformed_2, transformed_3)
def test_likelihood_check():
"""Test enable doc_likelihood check
The result should be the same no matter it
is True or False.
"""
X = make_uniform_doc_word_matrix(n_topics=10,
words_per_topic=3,
docs_per_topic=3)
params = {
'n_topic_truncate': 20,
'n_doc_truncate': 5,
'learning_method': 'batch',
'max_iter': 10,
'random_state': 1,
'check_doc_likelihood': True,
'evaluate_every': 1,
}
hdp1 = HierarchicalDirichletProcess(**params)
ret1 = hdp1.fit_transform(X)
params['check_doc_likelihood'] = False
hdp2 = HierarchicalDirichletProcess(**params)
ret2 = hdp2.fit_transform(X)
assert_almost_equal(ret1, ret2)
def test_hdp_fit_transform():
"""Test HDP fit_transform"""
X = make_uniform_doc_word_matrix(n_topics=10,
words_per_topic=3,
docs_per_topic=3)
params = {
'n_topic_truncate': 20,
'n_doc_truncate': 5,
'learning_method': 'batch',
'max_iter': 10,
'random_state': 1,
}
hdp1 = HierarchicalDirichletProcess(**params)
hdp1.fit(X)
transformed_1 = hdp1.transform(X)
hdp2 = HierarchicalDirichletProcess(**params)
transformed_2 = hdp2.fit_transform(X)
assert_almost_equal(transformed_1, transformed_2)